Qwen2.5-1.5B-Open-R1-GRPO / all_results.json
Studyboy's picture
Model save
f94f70d verified
raw
history blame contribute delete
199 Bytes
{
"total_flos": 0.0,
"train_loss": 0.3329694670855358,
"train_runtime": 11851.6394,
"train_samples": 1494,
"train_samples_per_second": 0.126,
"train_steps_per_second": 0.016
}